@ingglish/ipa 0.1.0

package/dist/index.d.cts

@@ -0,0 +1,66 @@
+import { OutputFormat, TranslatedToken } from '@ingglish/phonemes';
+
+interface IpaDict {
+    entries: Record<string, string>;
+    lang: string;
+}
+interface Language {
+    code: string;
+    label: string;
+}
+/** Insert spaces between adjacent Khmer words that have no separator. */
+declare function segmentKhmerText(text: string): string;
+declare const LANGUAGES: Language[];
+/**
+ * Converts an IPA transcription to Ingglish spelling.
+ * Strips slashes and syllable dots before conversion.
+ */
+declare function ipaToIngglish(ipa: string): string;
+declare function lookupIpa(dict: IpaDict, word: string): string | undefined;
+/** Marker for words not found in the dictionary */
+declare const NOT_FOUND_MARKER = "\uFFFD";
+/**
+ * Translates foreign text to the specified output format.
+ * Words not found in the dictionary are returned with a marker prefix.
+ *
+ * For caseless scripts (Arabic, Japanese, Chinese, Korean), sentence-initial
+ * words are automatically capitalized in the output.
+ */
+declare function translateForeign(text: string, dict: IpaDict, format?: OutputFormat): string;
+/**
+ * Like {@link translateForeign}, but returns token-by-token mappings instead of a string.
+ * Each token includes the original text, translation, and whether it matched the dictionary.
+ */
+declare function translateForeignWithMapping(text: string, dict: IpaDict, format?: OutputFormat): TranslatedToken[];
+
+/**
+ * Converts IPA text to ARPAbet with stress digits stripped.
+ */
+declare function ipaToArpabetClean(ipa: string): null | string[];
+
+/**
+ * ARPAbet to IPA conversion.
+ *
+ * Converts CMU dictionary phoneme sequences to IPA notation,
+ * with proper stress marker placement at syllable boundaries.
+ */
+/**
+ * Converts a single ARPAbet phoneme to IPA.
+ * Handles stress markers on vowels.
+ *
+ * @param phoneme ARPAbet phoneme (e.g., "AH0", "EY1", "B")
+ * @returns IPA symbol (e.g., "ə", "ˈeɪ", "b")
+ */
+declare function arpabetPhonemeToIPA(phoneme: string): string;
+/**
+ * Converts ARPAbet to IPA without surrounding slashes.
+ * Useful for combining with other text.
+ *
+ * @param arpabet Array of ARPAbet symbols
+ * @returns IPA transcription without surrounding slashes
+ */
+declare function arpabetToIPARaw(arpabet: string[]): string;
+
+declare function registerIPA(): void;
+
+export { type IpaDict, LANGUAGES, type Language, NOT_FOUND_MARKER, arpabetPhonemeToIPA, arpabetToIPARaw, ipaToArpabetClean, ipaToIngglish, lookupIpa, registerIPA, segmentKhmerText, translateForeign, translateForeignWithMapping };

package/dist/index.d.ts

@@ -0,0 +1,66 @@
+import { OutputFormat, TranslatedToken } from '@ingglish/phonemes';
+
+interface IpaDict {
+    entries: Record<string, string>;
+    lang: string;
+}
+interface Language {
+    code: string;
+    label: string;
+}
+/** Insert spaces between adjacent Khmer words that have no separator. */
+declare function segmentKhmerText(text: string): string;
+declare const LANGUAGES: Language[];
+/**
+ * Converts an IPA transcription to Ingglish spelling.
+ * Strips slashes and syllable dots before conversion.
+ */
+declare function ipaToIngglish(ipa: string): string;
+declare function lookupIpa(dict: IpaDict, word: string): string | undefined;
+/** Marker for words not found in the dictionary */
+declare const NOT_FOUND_MARKER = "\uFFFD";
+/**
+ * Translates foreign text to the specified output format.
+ * Words not found in the dictionary are returned with a marker prefix.
+ *
+ * For caseless scripts (Arabic, Japanese, Chinese, Korean), sentence-initial
+ * words are automatically capitalized in the output.
+ */
+declare function translateForeign(text: string, dict: IpaDict, format?: OutputFormat): string;
+/**
+ * Like {@link translateForeign}, but returns token-by-token mappings instead of a string.
+ * Each token includes the original text, translation, and whether it matched the dictionary.
+ */
+declare function translateForeignWithMapping(text: string, dict: IpaDict, format?: OutputFormat): TranslatedToken[];
+
+/**
+ * Converts IPA text to ARPAbet with stress digits stripped.
+ */
+declare function ipaToArpabetClean(ipa: string): null | string[];
+
+/**
+ * ARPAbet to IPA conversion.
+ *
+ * Converts CMU dictionary phoneme sequences to IPA notation,
+ * with proper stress marker placement at syllable boundaries.
+ */
+/**
+ * Converts a single ARPAbet phoneme to IPA.
+ * Handles stress markers on vowels.
+ *
+ * @param phoneme ARPAbet phoneme (e.g., "AH0", "EY1", "B")
+ * @returns IPA symbol (e.g., "ə", "ˈeɪ", "b")
+ */
+declare function arpabetPhonemeToIPA(phoneme: string): string;
+/**
+ * Converts ARPAbet to IPA without surrounding slashes.
+ * Useful for combining with other text.
+ *
+ * @param arpabet Array of ARPAbet symbols
+ * @returns IPA transcription without surrounding slashes
+ */
+declare function arpabetToIPARaw(arpabet: string[]): string;
+
+declare function registerIPA(): void;
+
+export { type IpaDict, LANGUAGES, type Language, NOT_FOUND_MARKER, arpabetPhonemeToIPA, arpabetToIPARaw, ipaToArpabetClean, ipaToIngglish, lookupIpa, registerIPA, segmentKhmerText, translateForeign, translateForeignWithMapping };